A packet forwarding network may include spine and leaf switches that forward network traffic between end hosts that are coupled to the packet forwarding network. A controller may control the switches in the forwarding network to implement desired forwarding paths. The packet forwarding network may additionally include access switches that are directly connected to edge switches to form access switch groups. The access switches may also be controlled by the controller. End hosts may be coupled to access switches as well as leaf switches to extend the reach of the packet forwarding network. Additionally, the access switches may include access-leaf switches and access-edge switches to improve network routing capabilities and network flexibility.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method of operating a controller to control a network having a leaf switch implemented on a network rack, a spine switch coupled to the leaf switch, and an access switch coupled to the leaf switch the method comprising: with the controller, identifying an end host directly coupled to a port of the access switch and identifying a port of the leaf switch directly coupled to an additional port of the access switch, wherein the access switch is implemented on switching circuitry separate from the network rack; and with the controller, controlling the access switch to forward network traffic between the end host and the spine switch via the leaf switch.
2. The method defined in claim 1 , wherein the leaf switch is coupled between the access switch and the spine switch, and an additional leaf switch implemented on the network rack is coupled between the access switch and the spine switch.
3. The method defined in claim 2 , further comprising: with the controller, controlling the access switch to forward the network traffic between the end host and the spine switch via the additional leaf switch.
4. The method defined in claim 3 , further comprising: with the controller, identifying an additional end host that is implemented on the network rack and that is directly coupled to at least one of the leaf switch or the additional leaf switch, wherein the end host is implemented separately from the network rack.
5. The method defined in claim 4 , further comprising: with the controller, controlling the access switch to forward network traffic between the end host and the additional end host through the one of the leaf switch or the additional leaf switch to which the additional end host is directly coupled.
6. The method defined in claim 2 , wherein an additional access switch is coupled to the access switch to form an access group, the leaf switch is coupled between the additional access switch and the spine switch, and the additional leaf switch is coupled between the additional access switch and the spine switch.
7. The method defined in claim 1 , wherein the access switch is not directly connected to the spine switch.
8. A method of using a controller that controls switches in a packet forwarding network including an access switch group, a core switch, and an edge switch coupled between the access switch group and the core switch the method comprising: with the controller, identifying a first access switch in the access switch group having a first link to the edge switch; with the controller, identifying a second access switch in the access group having a second link to the edge switch; and with the controller, identifying a peer access switch link between the first and second access switches.
9. The method defined in claim 8 , further comprising: with the controller, configuring the core switch with a first setting associated with a first switch type; and with the controller, configuring the edge switch with a second setting associated with a second switch type that is different from the first switch type.
10. The method defined in claim 9 , further comprising: with the controller, configuring the first and second access switches with a third setting associated with a third switch type that is different from the first and second switch types.
11. The method defined in claim 10 , wherein switches of the first switch type are only coupled to other switches, and switches of the second and third types are coupled to end hosts and other switches.
12. The method defined in claim 8 , further comprising: with the controller, identifying a third access switch in the access switch group coupled to the edge switch through at least one of the first access switch or the second access switch.
13. The method defined in claim 12 , further comprising: with the controller, identifying end hosts directly coupled to the edge switch, the first access switch, the second access switch, and the third access switch.
14. The method defined in claim 8 , wherein the edge switch and an additional edge switch are implemented as top-of-rack switches for a network rack, and the additional edge switch is coupled between the access switch group and the core switch.
15. The method defined in claim 8 , further comprising: with the controller, identifying an additional access switch group that is indirectly connected to the access switch group through the edge switch.
16. A method of operating computing equipment to control switches in a network having end hosts that are coupled to ports of the switches, the method comprising: with the computing equipment, identifying a first set of switches, each of which is coupled to each of the end hosts through at least one connecting switch, as a core switch type; with the computing equipment, identifying a second set of switches, at least a portion of which is directly coupled to a portion of the end hosts, as an edge switch type, wherein the at least one connecting switch comprises one of the second set of switches; and with the computing equipment, identifying a third set of switches, each of which is coupled to each switch of the core switch type through at least one intervening switch and at least a portion of which is directly coupled to an additional portion of the end hosts, as an access switch type, wherein the at least one intervening switch comprises a switch in the second set of switches.
17. The method defined in claim 16 , wherein the second set of switches are implemented on a plurality of network racks.
18. The method defined in claim 17 , wherein the third set of switches are implemented on switching circuitry separate from the plurality of network racks.
19. The method defined in claim 16 , wherein the identifying the third set of switches comprises: identifying switches of a first subtype in the third set of switches that are directly coupled to at least one of the switches in the second set of switches; and identifying switches of a second subtype in the third set of switches that are coupled to at least one of the switches in the second set of switches through a correspond switch in the switches of the first subtype.
20. The method defined in claim 19 , wherein a first end host in the additional portion of the end hosts is directly coupled to a switch in the switches of the first subtype and a second end host in the additional portion of the end hosts is directly coupled to a switch in the switches of the second subtype.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
December 31, 2018
December 22, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.